项目作者: harsh306

项目描述 :
Implementation of "Parameter Continuation Methods for the Optimization of Deep Neural Networks" accepted at ICMLA 19. https://ieeexplore.ieee.org/abstract/document/8999318
高级语言: Jupyter Notebook
项目地址: git://github.com/harsh306/NPACS.git
创建时间: 2019-01-26T19:37:14Z
项目社区:https://github.com/harsh306/NPACS

开源协议:

下载


File ae.py contains the modal and TF graph.

File npc.py contains Natural parameter continuation (NPC) method (without secant).

File main.py contains NPCS method with secant.

File ops2.py contains basic operations.

File example.json has list of hyperparameter to tune.

Folder csmote has the code for Continuous-SMOTE.